Skip to main content

This lecture covers advanced concepts of energy-based models. The lecture is a part of the Associative Memories module of the the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this course include: Energy-Based Models IEnergy-Based Models IIEnergy-Based Models IIIEnergy-Based Models IV, Energy-Based Models V, and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 2:00:28
Speaker: : Yann LeCun

This tutorial covers advanced concept of energy-based models. The lecture is a part of the Associative Memories module of the the Deep Learning Course at NYU's Center for Data Science. 

Difficulty level: Advanced
Duration: 1:12:00
Speaker: : Alfredo Canziani

This lecture provides an introduction to the problem of speech recognition using neural models, emphasizing the CTC loss for training and inference when input and output sequences are of different lengths. It also covers the concept of beam search for use during inference, and how that procedure may be modeled at training time using a Graph Transformer Network. It is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Modules 1 - 5 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 1:55:03
Speaker: : Awni Hannun

This lecture covers the concepts of the architecture and convolution of traditional convolutional neural networks, the characteristics of graph and graph convolution, and spectral graph convolutional neural networks and how to perform spectral convolution, as well as the complete spectrum of Graph Convolutional Networks (GCNs), starting with the implementation of Spectral Convolution through Spectral Networks. It then provides insights on applicability of the other convolutional definition of Template Matching to graphs, leading to Spatial networks. This lecture is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Modules 1 - 5 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 2:00:22
Speaker: : Xavier Bresson

This tutuorial covers the concept of graph convolutional networks and is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Modules 1 - 5 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 57:33
Speaker: : Alfredo Canziani

This lecture covers the concept of model predictive control and is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Models 1-6 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 1:10:22
Speaker: : Alfredo Canziani

This lecture covers the concepts of emulation of kinematics from observations and training a policy. It is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Models 1-6 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 1:01:21
Speaker: : Alfredo Canziani

This lecture covers the concept of predictive policy learning under uncertainty and is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Models 1-6 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 1:14:44
Speaker: : Alfredo Canziani

This lecture covers the concepts of gradient descent, stochastic gradient descent, and momentum. It is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Models 1-7 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 1:29:05
Speaker: : Aaron DeFazio

This lecture continues on the topic of descent from the previous lesson, Optimization I. This lesson is a part of the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this module include: Models 1-7 of this course and an Introduction to Data Science or a Graduate Level Machine Learning course.

Difficulty level: Advanced
Duration: 1:51:32
Speaker: : Alfredo Canziani

This tutorial demonstrates how to work with neuronal data using MATLAB, including actional potentials and spike counts, orientation tuing curves in visual cortex, and spatial maps of firing rates.

Difficulty level: Intermediate
Duration: 5:17
Speaker: : Mike X. Cohen

This lesson instructs users on how to import electrophysiological neural data into MATLAB, as well as how to convert spikes to a data matrix.

Difficulty level: Intermediate
Duration: 11:37
Speaker: : Mike X. Cohen

In this lesson, users will learn how to appropriately sort and bin neural spikes, allowing for the generation of a common and powerful visualization tool in neuroscience, the histogram. 

Difficulty level: Intermediate
Duration: 5:31
Speaker: : Mike X. Cohen

Followers of this lesson will learn how to compute, visualize and quantify the tuning curves of individual neurons. 

Difficulty level: Intermediate
Duration: 13:48
Speaker: : Mike X. Cohen

This lesson demonstrates how to programmatically generate a spatial map of neuronal spike counts using MATLAB.

Difficulty level: Intermediate
Duration: 12:16
Speaker: : Mike X. Cohen

In this lesson, users will learn about human brain signals as measured by electroencephalography (EEG), as well as associated neural signatures such as steady state visually evoked potentials (SSVEPs) and alpha oscillations. 

Difficulty level: Intermediate
Duration: 8:51
Speaker: : Mike X. Cohen

This lecture describes the principles of EEG electrode placement in both 2- and 3-dimensional formats. 

Difficulty level: Intermediate
Duration: 12:16
Speaker: : Mike X. Cohen

This tutorial walks users through performing Fourier Transform (FFT) spectral analysis of a single EEG channel using MATLAB. 

Difficulty level: Intermediate
Duration: 13:39
Speaker: : Mike X. Cohen

This tutorial builds on the previous lesson's demonstration of spectral analysis of one EEG channel. Here, users will learn how to compute and visualize spectral power from all EEG channels using MATLAB. 

Difficulty level: Intermediate
Duration: 12:34
Speaker: : Mike X. Cohen

In this lesson, users will learn more about the steady-state visually evoked potential (SSEVP), as well as how to create and interpret topographical maps derived from such studies. 

Difficulty level: Intermediate
Duration: 9:10
Speaker: : Mike X. Cohen